Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Hostages leverage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ‹
    -0.08
    elä
    -0.08
    ústrias
    -0.08
    ‹
    -0.08
    HING
    -0.08
    émie
    -0.08
    >(*
    -0.08
    ме
    -0.08
    �
    -0.08
    Ё
    -0.08
    POSITIVE LOGITS
     soon
    0.08
    ersu
    0.08
     معهم
    0.07
     Kuz
    0.07
    Rare
    0.07
    977
    0.07
     promising
    0.07
     rare
    0.07
    servers
    0.07
     bewijs
    0.07
    Act Density 0.005%

    No Known Activations